Skip to content

Trieste API Reference

Installation and usage

sb_arch_opt.algo.trieste_interface.api.get_trieste_optimizer(problem: ArchOptProblemBase, n_init: int, n_infill: int, pof: float = 0.5, seed: int = None)

Gets the main interface to Trieste. Use the run_optimization method to run the DOE and infill loops.

sb_arch_opt.algo.trieste_interface.algo.ArchOptBayesianOptimizer(problem: ArchOptProblemBase, n_init: int, n_infill: int, pof=0.5, rule: AcquisitionRule = None, seed: int = None)

Bayesian optimization loop controller with some extra helper functions. Use the run_optimization function to run the DOE and infill loops. Use initialize_from_previous to initialize the optimization state from previously saved results.

Optimization loop: https://secondmind-labs.github.io/trieste/2.0.0/notebooks/expected_improvement.html Restart: https://secondmind-labs.github.io/trieste/2.0.0/notebooks/recovering_from_errors.html Constraints: https://secondmind-labs.github.io/trieste/2.0.0/notebooks/inequality_constraints.html Multi-objective: https://secondmind-labs.github.io/trieste/2.0.0/notebooks/multi_objective_ehvi.html Hidden constraints: https://secondmind-labs.github.io/trieste/2.0.0/notebooks/failure_ego.html Ask-tell: https://secondmind-labs.github.io/trieste/2.0.0/notebooks/ask_tell_optimization.html

initialize_from_previous(results_folder: str)

run_optimization(results_folder=None) -> Record

Runs a full optimization, including initial DOE

to_population(datasets: Dict[Hashable, Dataset]) -> Population